相关论文: LSTM Acoustic Models Learn to Align and Pronounce …

Language models are typically trained on large corpora of text in their default orthographic form. However, this is not the only option; representing data as streams of phonemes can offer unique advantages, from deeper insights into…

Large-scale pre-trained language models have been shown to be helpful in improving the naturalness of text-to-speech (TTS) models by enabling them to produce more naturalistic prosodic patterns. However, these models are usually word-level…

Modeling the relationship between natural speech and a recorded electroencephalogram (EEG) helps us understand how the brain processes speech and has various applications in neuroscience and brain-computer interfaces. In this context, so…

While speech recognition has seen a surge in interest and research over the last decade, most machine learning models for speech recognition either require large training datasets or lots of storage and memory. Combined with the prominence…

Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations. In this paper, we describe a system for automatically obtaining pronunciations of words for which pronunciations are not…

Aligning acoustic and linguistic representations is a central challenge to bridge the pre-trained models in knowledge transfer for automatic speech recognition (ASR). This alignment is inherently structured and asymmetric: while multiple…

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been reported by prepending…

Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on…

Textless spoken language models (SLMs) are generative models of speech that do not rely on text supervision. Most textless SLMs learn to predict the next semantic token, a discrete representation of linguistic content, and rely on a…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

This article presents a whisper speech detector in the far-field domain. The proposed system consists of a long-short term memory (LSTM) neural network trained on log-filterbank energy (LFBE) acoustic features. This model is trained and…

Machine learning models allow us to compare languages by showing how hard a task in each language might be to learn and perform well on. Following this line of investigation, we explore what makes a language "hard to pronounce" by modelling…

Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based…

Recent progress in Spoken Language Modeling has shown that learning language directly from speech is feasible. Generating speech through a pipeline that operates at the text level typically loses nuances, intonations, and non-verbal…

Models of acoustic word embeddings (AWEs) learn to map variable-length spoken word segments onto fixed-dimensionality vector representations such that different acoustic exemplars of the same word are projected nearby in the embedding…

In the traditional cascading architecture for spoken language understanding (SLU), it has been observed that automatic speech recognition errors could be detrimental to the performance of natural language understanding. End-to-end (E2E) SLU…

In the realm of spoken language understanding (SLU), numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional written text. In…

With the rise of Large Language Models (LLMs) and their vision-enabled counterparts (VLMs), numerous works have investigated their capabilities in tasks that fuse the modalities of vision and language. In this work, we benchmark the extent…

Integrating large language models (LLMs) with knowledge graphs derived from domain-specific data represents an important advancement towards more powerful and factual reasoning. As these models grow more capable, it is crucial to enable…